Grayscale-inversion and rotation invariant image description using local ternary derivative pattern with dominant structure encoding

作者：

Highlights：

• We propose a grayscale-inversion and rotation invariant image descriptor.

• The neighboring relationship is encoded based on Gaussian derivative filters.

• Adaptive ternary quantization and extended non-split ternary encoding are adopted.

• The dominant structure encoding is used to enhance the discriminative ability.

摘要

•We propose a grayscale-inversion and rotation invariant image descriptor.•The neighboring relationship is encoded based on Gaussian derivative filters.•Adaptive ternary quantization and extended non-split ternary encoding are adopted.•The dominant structure encoding is used to enhance the discriminative ability.

论文关键词：Texture,Image feature,Illumination invariance,Rotation invariance,Local binary pattern,Local ternary pattern

论文评审过程：Received 6 May 2020, Revised 21 November 2021, Accepted 26 November 2021, Available online 11 December 2021, Version of Record 16 December 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116327